© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 15683
    Prev
    Next
    INDEX
    Explanations

    list of specific examples or concepts

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron is picking out numeric tokens (instances of digits or numbers).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ur
    0.70
    an
    0.68
    ل
    0.65
    ت
    0.64
    الم
    0.63
    Р
    0.60
    o
    0.59
     the
    0.59
    ن
    0.59
                
    0.58
    POSITIVE LOGITS
    ️⃣
    0.72
     vetting
    0.55
     blurring
    0.54
    %");
    0.53
    %).
    0.52
     rxjs
    0.52
    %)
    0.51
     dimensionless
    0.50
     anecdote
    0.49
    xbet
    0.49
    Activations Density 0.510%

    No Known Activations